Self-Tuning Neuro-PID for Stabilization of Double Inverted Pendulum
Yoshiyuki Kishida, Sigeru Omatu and Michifumi Yoshioka
Department of Computer and Systems Sciences, College of Engineering, Osaka Prefecture University, Sakai, Osaka 599-8531, Japan
This paper covers a new self-tuning neuro-PID control architecture and its application to stabilization of single and double inverted pendulums. Single-Input multioutput controls the inverted pendulum using the PID controller. PID gains are tuned using two types of neural networks. Simulation results demonstrate the effectiveness of the proposed approach.